-
# 🐛 Bug
Despite my model and all tensors in the script being on the GPU, fit_gpytorch_model complains about tensors existing on both cuda:0 and CPU.
## To reproduce
This code works when I ju…
-
Hi All,
**TL;DR** :bug: If your model involves using a `full_backward_hook`, computing derivatives throws a missing `setup_context` error. As a full backward hook is technically a `torch.autograd.F…
-
## 🚀 Feature Request
Earth Mover's Distance (EMD) is a popular loss metric for comparing point clouds alongside Chamfer Distance. Popular studies [1,2] use both distances for point cloud generation a…
-
A narrow issue, but sorting this out will probably provide a pretty good template for other issues. The current issues are:
- [x] Incorrect answers/errors for power series
- [x] #102
- [x] Incorr…
-
In Sage 9.3, we have
```
sage: E. = EuclideanSpace()
sage: polar. = E.polar_coordinates()
sage: g = E.metric()
sage: M = Manifold(1, 'M')
sage: Ct. = M.chart()
sage: F = M.diff_map(E, coord_functio…
-
Now that sparse tensors are mostly working (https://github.com/pytorch/pytorch/pull/1147), it would be awesome if all the optimizers worked with sparse tensors. This requires some cleverness to do amo…
-
# 🚀 Feature
Hello! Currently, the library seems to only support one kind of masking: `xformers.ops.LowerTriangularMask`. Only one attention strategy (`small_k`) supports arbitrary tensors.
I gath…
-
In response to https://leanprover-community.github.io/archive/stream/208328-IMO-grand-challenge/topic/Current.20status.3F.html#320982506
@**Mario Carneiro** I think models like the [Toolformer](htt…
-
At present differential forms are dealt with by different and incompatible parts of Sage: the [CoordinatePatch version](http://doc.sagemath.org/html/en/reference/tensor/sage/tensor/differential_form…
-
When compiling [Modelica.Electrical.Analog.Examples.OpAmps.Comparator](https://libraries.openmodelica.org/branches/newInst-newBackend/Modelica_4.0.0/files/Modelica_4.0.0_Modelica.Electrical.Analog.Exa…